outcome of a user clicking on an online advertisement.
Download the Advertising dataset from Kaggle.com (
www.kaggle.com/fayomi/advertising/data) and load it into your jupyter notebook.
Task 1: Data Analysis [1′]
Step 1: Remove two text variables ‘Ad Topic Line’ and ‘Timestamp’ from the dataframe.
Step 2: Use one-hot encoding to convert ‘Country’ and ‘City’ variables to numeric values.
Task 2: Machine Learning with SVM [5′]
Step 1: Assign training data and labels.
Make ‘Click on Ad’ as labels; use the remaining variables as data.
Step 2: Train Test Split.
Split the training data into training and test sets with train_test_split().
Set parameter test_size = 0.3, random_state to the last two digits of your student ID. (e.g., suppose
your student id is S00123410, then, set random_state = 10)
Please attach your name and student id in a separate markdown cell as a proof.
Step 3: Training and Fitting the model. Predictions from the trained model.
Set up the classification model, SVM, with Scikit-learn. Train the model with training data. Make
predictions on the test set.
Step 4: Model Evaluation
Evaluate your prediction with confusion_matrix() and classification_report()
Read more here: Source link